Skip to main content
POST
/
v1
/
test-cases
Create Test Case
curl --request POST \
  --url https://api.sigmamind.ai/v1/test-cases \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '
{
  "agentId": "D5D0p7TUs66TTAEAx",
  "userPrompt": "You are an angry customer who wants to cancel his subscription. ",
  "successCriteria": "Agent should acknowledge the request, offer alternatives, and confirm cancellation if the user insists.",
  "llmModel": "gpt-4o-mini",
  "mockData": [
    {
      "variableName": "customer_name",
      "value": "John Doe"
    },
    {
      "variableName": "account_status",
      "value": "active"
    }
  ],
  "attempt": 5
}
'
{
  "testCaseId": "tc_d17T6uReChpyfFeP",
  "agent": {
    "name": "Demo Agent",
    "agentId": "mJzLaPEo425lieb9",
    "status": "Testing"
  },
  "workspaceId": "org_V6eZ2zg8ziDx5pft",
  "llmModel": "gpt-4o-mini",
  "mockData": [
    {
      "variableName": "customer_name",
      "value": "John Doe"
    },
    {
      "variableName": "account_status",
      "value": "active"
    }
  ],
  "userPrompt": "You are an angry customer who wants to cancel his subscription. ",
  "attempt": 5,
  "successCriteria": "Agent should acknowledge the request, offer alternatives, and confirm cancellation if the user insists."
}

Authorizations

​
X-API-Key
string
header
required

API Key is required in header. You can find it in the settings

Body

application/json
​
agentId
string
required

The unique identifier of the Agent assigned to handle the chat simulation.

Example:

"D5D0p7TUs66TTAEAx"

​
userPrompt
string
required

The user prompt that generates the user or customer messages in the chat simulation.

Example:

"You are an angry customer who wants to cancel his subscription. "

​
successCriteria
string
required

Criteria used to evaluate whether the agent successfully handled the conversation.

Example:

"Agent should acknowledge the request, offer alternatives, and confirm cancellation if the user insists."

​
llmModel
string

The LLM model used to generate Agent responses during the chat simulation. For priority models of OpenAI, please use the suffix '-fast-tier' after the model name, eg: gpt-4o-mini-fast-tier

Example:

"gpt-4o-mini"

​
mockData
object[]

List of mock data variables used to simulate external inputs during the chat.

Example:
[
  {
    "variableName": "customer_name",
    "value": "John Doe"
  },
  {
    "variableName": "account_status",
    "value": "active"
  }
]
​
attempt
integer<int64>

The number of times the simulation should run with this test case. Default is 1.

Example:

5

Response

OK

​
testCaseId
string

Unique identity for a test case

Example:

"tc_d17T6uReChpyfFeP"

​
agent
object

Assigned agent for current campaign

Example:
{
  "name": "Demo Agent",
  "agentId": "mJzLaPEo425lieb9",
  "status": "Testing"
}
​
workspaceId
string

Workspace to which the user belongs

Example:

"org_V6eZ2zg8ziDx5pft"

​
llmModel
string

LLM Model used to generate the Agent response during the chat simulation

Example:

"gpt-4o-mini"

​
mockData
object[]

List of mock data variables used to simulate external inputs during the chat.

Example:
[
  {
    "variableName": "customer_name",
    "value": "John Doe"
  },
  {
    "variableName": "account_status",
    "value": "active"
  }
]
​
userPrompt
string

User prompt used to generate the Customer queries during the chat simulation

Example:

"You are an angry customer who wants to cancel his subscription. "

​
attempt
integer<int64>

The number of times the chat simulation should run with this test case.

Example:

5

​
successCriteria
string

Criteria used to evaluate whether the agent successfully handled the conversation.

Example:

"Agent should acknowledge the request, offer alternatives, and confirm cancellation if the user insists."